THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The vision of next generation 5G wireless communications lies in providing very high data rates (typically of Gbps order), extremely low latency, manifold increase in base station capacity, and significant improvement in users’ perceived quality of service (QoS), compared to current 4G LTE networks. Ever increasing proliferation of smart devices, introduction of new emerging multimedia applications, together with an exponential rise in wireless data (multimedia) demand and usage is already creating a significant burden on existing cellular networks. 5G wireless systems, with improved data rates, capacity, latency, and QoS are expected to be the panacea of most of the current cellular networks’ problems. In this survey, we make an exhaustive review of wireless evolution toward 5G networks. We first discuss the new architectural changes associated with the radio access network (RAN) design, including air interfaces, smart antennas, cloud and heterogeneous RAN. Subsequently, we make an in-depth survey of underlying novel mm-wave physical layer technologies, encompassing new channel model estimation, directional antenna design, beamforming algorithms, and massive MIMO technologies. Next, the details of MAC layer protocols and multiplexing schemes needed to efficiently support this new physical layer are discussed. We also look into the killer applications, considered as the major driving force behind 5G. In order to understand the improved user experience, we provide highlights of new QoS, QoE, and SON features associated with the 5G evolution. For alleviating the increased network energy consumption and operating expenditure, we make a detail review on energy awareness and cost efficiency. As understanding the current status of 5G implementation is important for its eventual commercialization, we also discuss relevant field trials, drive tests, and simulation experiments. Finally, we point out major existing research issues and identify possible future research directions.

Next Generation 5G Wireless Networks: A Comprehensive Survey

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

The Object Management Group's (OMG) Model Driven Architecture (MDA) strategy envisages a world where models play a more direct role in software production, being amenable to manipulation and transformation by machine. Model Driven Engineering (MDE) is wider in scope than MDA. MDE combines process and analysis with architecture. This article sets out a framework for model driven engineering, which can be used as a point of reference for activity in this area. It proposes an organisation of the modelling 'space' and how to locate models in that space. It discusses different kinds of mappings between models. It explains why process and architecture are tightly connected. It discusses the importance and nature of tools. It identifies the need for defining families of languages and transformations, and for developing techniques for generating/configuring tools from such definitions. It concludes with a call to align metamodelling with formal language engineering techniques.

Model Driven Engineering

The inadequate quality of context forces the context consumers in pervasive environments to reason about the quality and relevance of context to be confident of its worth to perform their functionality. The additional task of analyzing large volumes of context drastically affects the performance of the context consumers to adjust to dynamically changing situations. A single value that presents the quality and relevance of context information tailored to the needs of a particular context consumer may release them from spending resources on context quality analysis and let them concentrate on their main task. In this paper we present a novel technique to combine different Quality of Context (QoC) metrics to infer the value of confidence on context. Our technique also considers the requirements of a particular context consumer regarding QoC metrics while confidence inference. Confidence on context is further provided to the context consumers to select high quality context and use the confidence in their functionality. We have successfully evaluated our approach using two context consumer services and user context collected from a smart home pervasive environment.

/pdf/service-centric-inference-and-utilization-of-confidence-on-4elr70thsw.pdf

Service-centric Inference and Utilization of Confidence on Context

A large number of cloud providers offer diverse types of cloud services for constructing complex ”cloud-native” software. However, there is a lack of supporting tools and mechanisms for accelerating the development of cloud-native software-defined elastic systems (SESs) based on elasticity capabilities of cloud services. In this paper we introduce QUELLE – a framework for evaluating and recommending SES deployment configurations. QUELLE presents models for describing the elasticity capabilities of cloud services and capturing elasticity requirements of SESs. Based on that QUELLE introduces novel functions and algorithms for quantifying the elasticity capabilities of cloud services. QUELLE’s algorithms can recommend SES deployment configurations from cloud services that both provide the required elasticity, and fulfill cost, quality, and resource requirements, and thus can be incorporated into different phases of the development of SESs. We present several experiments based on real-world cloud services for the development of an elastic machine-to-machine data-as-a-service system.

/pdf/quelle-a-framework-for-accelerating-the-development-of-40on76pufm.pdf

QUELLE – A Framework for Accelerating the Development of Elastic Systems

Modern development of computing systems caters the collaboration of human-based resources together with machine-based resources as active compute units. Those units can be dynamically provisioned on-demand for solving complex tasks, such as observed in collaborative applications, crowd sourced applications, and human task workflows. Such collaborations involve very diverse compute units, which have different capabilities and reliability. While the reliability analysis for machine-based compute units has been widely developed, the reliability analysis for the hybrid human-machine collaborations has not been extensively studied. In this paper we present models and a framework for analyzing the reliability of hybrid compute units (HCU), which represent on-demand collectives of humans collaboration supported by machines (hardware and software units) for performing tasks. We present the implementation of our models and study the reliability of HCUs in a simulated system for infrastructure maintenance scenarios. Our evaluation shows that the proposed framework is effective for measuring the reliability of the collaboration collectives, and beneficial to obtain insights for improvements.

/pdf/analyzing-reliability-in-hybrid-compute-units-170sjvp97l.pdf

Analyzing Reliability in Hybrid Compute Units

Combining software-based and human-based services is crucial for several complex problems that cannot be solved using software-based services alone. In this paper, we present novel methods for modeling and developing hybrid compute units of software-based and human-based services. We discuss high-level programming elements for different types of software- and human-based service units and their relationships. In particular, we focus on novel programming elements reflecting hybridity, collectiveness and adaptiveness properties, such as elasticity and social connection dependencies, and on-demand and pay-per-use economic properties, such as cost, quality and benefits, for complex problem solving. Based on these programming elements, we present programming constructs and patterns for building complex applications using hybrid services.

/pdf/augmenting-complex-problem-solving-with-hybrid-compute-units-2vef5qy2nl.pdf

Augmenting Complex Problem Solving with Hybrid Compute Units

The analysis of massive amounts of diverse data provided by large cities, combined with the requirements from multiple domain experts and users, is becoming a challenging trend. Although current process-based solutions rise in data awareness, there is less coverage of approaches dealing with the Quality-of-Result (QoR) to assist data analytics in distributed data-intensive environments. In this paper, we present the fundamental building blocks of a framework for enabling process selection and configuration through user-defined QoR at runtime. These building blocks form the basis to support modeling, execution and configuration of data-aware process variants in order to perform analytics. They can be integrated with different underlying APIs, promoting abstraction, QoR-driven data interaction and configuration. Finally, we carry out a preliminary evaluation on the URBEM scenario, concluding that our framework spends little time on QoR-driven selection and configuration of data-aware processes.

/pdf/drain-an-engine-for-quality-of-result-driven-process-based-57f9h844su.pdf

Hong-Linh Truong

Papers

Service-centric Inference and Utilization of Confidence on Context

QUELLE – A Framework for Accelerating the Development of Elastic Systems

Analyzing Reliability in Hybrid Compute Units

Augmenting Complex Problem Solving with Hybrid Compute Units

DRain: An Engine for Quality-of-Result Driven Process-Based Data Analytics